Today, we're opening up Lilian for anyone to try.
Visit trylilian.vectoragents.ai and see what prospect discovery looks like when it's built on 200+ signals — not a filtered database.
Here's what that actually means.
Most sales teams build prospect lists the same way.
They open a database. They filter by job title. They add company size. They narrow by industry and geography. Maybe they layer in a few extra signals — hiring activity, recent funding, M&A announcements — if they're being thorough.
Then they export the list and start reaching out.
The problem isn't the process. It's that every other sales team is running the same process, on the same databases, with the same filters.
Which means you're all chasing the same people. At the same time. With roughly the same message.
The result is predictable: reply rates drop, prospects get fatigued, and your outbound starts to feel like noise even when your product is genuinely relevant.
The issue isn't the outreach. It's the list. And the list is only as good as the signals underneath it.
Lilian doesn't query a static database. She triangulates.
Where a standard prospecting tool might look at three or four dimensions — title, company, size, industry — Lilian pulls from a far wider surface: activity patterns, interests, trade data, technology stacks, hiring behaviour, lifestyle signals, and other publicly available indicators across 200+ data points.
This matters for two reasons.
First, the leads are different. When you're drawing from richer context, you surface prospects that don't appear on everyone else's list. Not because they're hidden — because they haven't been matched against signals that most tools don't track.
Second, you know why they appeared. This is the part that changes how you reach out.
Lilian doesn't just surface a name and a company. She shows you the signal and source behind the result — why that person showed up in your search, what specifically triggered the match. So when you write your outreach, you're not writing to a job title. You're writing to a context.
That's the difference between a message that lands and one that gets archived.
The best-performing outbound isn't sent to the most people. It's sent to the right people at the right moment.
Job title tells you what someone does. Signals tell you what they're doing right now — what they're hiring for, what tools they're evaluating, what markets they're entering, what problems they're visibly trying to solve.
A VP of Sales is always a VP of Sales. But a VP of Sales who just posted about scaling their outbound team, whose company just raised a Series B, and whose current tech stack doesn't include an AI SDR — that's a different conversation entirely.
That context is what Lilian is built to find. And it's what makes the difference between a generic list and a powerful one.
We're opening this up so people can see what's possible.
At [trylilian.vectoragents.ai](https://trylilian.vectoragents.ai), you can run searches using the kind of richer criteria that standard prospecting tools don't support — and see the signal layer behind every result.
You don't need to commit to anything. The point is to explore what changes when your prospect discovery is built on context, not just columns.
If the lists you're currently building feel like everyone else's lists — this is worth ten minutes of your time.
Most prospect lists are filtered spreadsheets.
They're useful. But they're also identical to the list your competitor built this morning, from the same database, with the same filters.
Lilian was built to change that. Not by finding a better database, but by drawing on a wider signal set — and by being transparent about why each prospect matched, so the intelligence carries through to the outreach.
Today, that's open to explore.
.svg)
.svg)
Vector AI All rights reserved. © 2025
.jpeg)